CN107478340B - A kind of converter valve monitoring method and system based on image co-registration - Google Patents
A kind of converter valve monitoring method and system based on image co-registration Download PDFInfo
- Publication number
- CN107478340B CN107478340B CN201710612787.0A CN201710612787A CN107478340B CN 107478340 B CN107478340 B CN 107478340B CN 201710612787 A CN201710612787 A CN 201710612787A CN 107478340 B CN107478340 B CN 107478340B
- Authority
- CN
- China
- Prior art keywords
- image
- converter valve
- visible images
- temperature area
- infrared
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000012544 monitoring process Methods 0.000 title claims abstract description 28
- 238000012545 processing Methods 0.000 claims description 20
- 230000008859 change Effects 0.000 claims description 7
- 238000005286 illumination Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 2
- 238000005070 sampling Methods 0.000 claims description 2
- 206010044565 Tremor Diseases 0.000 claims 1
- 230000004927 fusion Effects 0.000 abstract description 15
- 230000011218 segmentation Effects 0.000 abstract description 3
- 238000003672 processing method Methods 0.000 abstract 1
- 230000000694 effects Effects 0.000 description 8
- 238000003384 imaging method Methods 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000010187 selection method Methods 0.000 description 2
- 230000006641 stabilisation Effects 0.000 description 2
- 238000011105 stabilization Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000003483 aging Methods 0.000 description 1
- 238000005267 amalgamation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000002513 implantation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000002844 melting Methods 0.000 description 1
- 230000008018 melting Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012634 optical imaging Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/10—Radiation pyrometry, e.g. infrared or optical thermometry using electric radiation detectors
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N25/00—Investigating or analyzing materials by the use of thermal means
- G01N25/72—Investigating presence of flaws
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Radiation Pyrometers (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The present invention relates to a kind of converter valve monitoring method and system based on image co-registration, converter valve components are subjected to region segmentation, and temperature area was filtered out according to the infrared image in each region, for the pixel weighting fusion treatment for crossing temperature area progress visible images and infrared image, the image merged.This method does not need to improve the resolution ratio of infrared detector, cost can be effectively reduced, to quickly recognize the specific location and surface characteristics of converter valve exception excess temperature；Meanwhile the processing method can be automatically processed by computer, not easy to make mistakes without too many artificial participation, high-efficient, real-time is high.Moreover, the present invention can retain scene information abundant, timely monitoring and early warning are provided for the safe and stable operation of converter valve equipment.
Description
Technical field
The invention belongs to technical field of ultrahigh voltage direct current, and in particular to a kind of change of current valve unit monitoring based on image co-registration
Method and system.
Background technique
D.C. high voltage transmission has the history of many years in China.With being constantly progressive for HVDC Transmission Technology, and permitted
The superiority that various aspects have AC system incomparable, so that direct current transportation is increasingly received by people.Power electronics skill
The rapid development of art and microelectric technique, high-pressure high-power thyristor come out, and thyristor valves and Control Technique of Microcomputer are straight
A large amount of application has been obtained in stream power transmission engineering, has effectively improved the runnability and reliability of direct current transportation, has been promoted straight
Flow the development of technology of transmission of electricity.
As the core equipment in DC transmission system, need to carry out converter valve equipment close monitoring.Currently, exchange
Valve monitoring is flowed, is concentrated mainly in the monitoring to transistors breakdown and the monitoring of valve tower water leakage situation, not further more
Perfect Stateful Inspection function.
Though design initial stage, the running temperature of the key components and parts of converter valve equipment is all designed normal range (NR) it
It is interior, still, due to failure problems such as the abnormal high pressure of equipment, component ageings, it still may cause the situation of running temperature exception
Occur.If being likely to result in device temperature without finding temperature anomaly point in time and sharply increasing or even occur on fire from explosion etc.
Major accident.In order to guarantee the safe and reliable operation of converter valve equipment, it is necessary to the operating statuses of converter valve key components and parts into
Row real-time monitoring finds temperature anomaly point in time, so as to take corresponding prevention, maintenance measure in time.
It is detected now frequently with heating accident of the thermal infrared imager to electric device.Any object for having temperature all can
Infrared ray is issued, thermal infrared imager is exactly the infrared energy that measured target is received using infrared detector and optical imaging objective
Amount distribution figure, reflects onto the light-sensitive element of infrared detector, measured object table can be shown by coloured picture
The Temperature Distribution in face.
And converter valve is high pressure, strong magnetic machine, valve layer space is limited, can not be by mature imaging device (such as infrared heat
As instrument) it is directly installed in valve tower.In order to solve this problem, it can generally be solved by two methods.First, pass through O&M people
The hand-held infrared equipment of member carries out the shooting of infrared image making an inspection tour aisle to converter valve, this method need it is artificial participate in, efficiency compared with
It is low, and the state of temperature of each components can not be directly measured, it is not able to satisfy the requirement of automatic running and real-time.Second,
Can integration imaging module implantation valve tower in, still, due to the temperature close of converter valve components electric elements inside, integration imaging mould
The universal pixel of block is lower, can not accurately identify the surface characteristics of components, if merely improving infrared detector resolution ratio, accordingly
Along with cost steeply rise and the appearance of some insoluble technical problems.
Summary of the invention
The purpose of the present invention is to provide a kind of converter valve monitoring method and system based on image co-registration, it is existing to solve
There is the problem that the low efficiency of converter valve equipment monitoring technology, real-time are low in technology.
In order to solve the above technical problems, the technical solution of the present invention is as follows:
A kind of converter valve monitoring method of the invention, includes the following steps:
1) infrared image and visible images of converter valve components are acquired；
2) converter valve components are divided at least two regions, and warm area was filtered out according to the infrared image in each region
Domain；
3) gray value of corresponding pixel points in the visible images for crossing temperature area and the infrared image for crossing temperature area is carried out
Weighted sum, the image merged；Wherein, it crosses the corresponding weight of visible images of temperature area and crosses the infrared figure of temperature area
As corresponding weight adds up to 1.
Further, when converter valve components are reactor area, the weight for crossing the visible images of temperature area is fixed value.
Further, when converter valve components are thyristor area, the weight and pixel ratio of the visible images of temperature area are crossed
Example is directly proportional；Wherein, the pixel ratio was standard drawing of the gray value lower than setting of the visible images pixel of temperature area
As the number of the gray value of pixel accounted for the ratio of the visible images total number of pixels of temperature area.
Further, step 2) includes: that the infrared image in each region is converted to temperature value, is searched in the region most
High-temperature, if maximum temperature is greater than temperature threshold when operating normally, which was temperature area.
Further, before step 3) further include: the infrared image for crossing temperature area is carried out image enhancement processing.
Further, before step 2) further include: the visible images of acquisition are carried out image enhancement processing.
Further, described image enhancing processing includes stabilization processing and image color processing.
Further, when the pixel ratio is lower than setting ratio, the visible images of acquisition are abandoned, by going through for storage
History visible images are as visible images to be fused.
Further, before step 2) further include: the visible images of acquisition and infrared image are carried out coaxial edge feature
Geometric precision correction processing.
A kind of change of current valve monitoring system of the invention, including acquisition unit and processor, the acquisition unit include visible
Light microscopic head and infrared lens；The processor sampling connects the visible light lens and infrared lens；
The visible light lens are used to acquire the visible images of converter valve components, and the infrared lens are for acquiring the change of current
The infrared image of valve module；
The processor is used to the infrared image of acquisition and visible images being divided at least two regions, and according to each
The infrared image in region filtered out temperature area；It will be corresponding in the visible images for crossing temperature area and the infrared image for crossing temperature area
The gray value of pixel is weighted summation, the image merged；Wherein, the corresponding weight of visible images of temperature area is crossed
Weight corresponding with the infrared image of temperature area is crossed adds up to 1.
The beneficial effects of the present invention are:
Converter valve components are carried out region segmentation by the converter valve monitoring method and system based on image co-registration of the invention,
And temperature area was filtered out according to each region infrared image of acquisition, for temperature area excessively, it will be seen that light image and infrared figure
As carrying out pixel weighting fusion treatment, the image merged.This method does not need to improve the resolution ratio of infrared detector, can
It is effectively reduced cost, to quickly recognize the specific location and surface characteristics of converter valve exception excess temperature；Meanwhile the processing side
Method can be automatically processed by computer, not easy to make mistakes without excessive artificial participation, high-efficient, and real-time is high.Moreover, this hair
It is bright to retain scene information abundant, timely monitoring and early warning are provided for the safe and stable operation of converter valve equipment.
Further, the present invention is according to the characteristic in different components regions, when carrying out pixel Weighted Fusion, using difference
Weight selection method, for the weight that the selection of volume biggish reactor area is fixed, for the thyristor area of small volume, choosing
Different weight coefficients is selected, the selection of the coefficient is related with pixel ratio, and pixel ratio was the visible images picture of temperature area
The gray value of element is always a lower than the visible images pixel that the number of the gray value of the standard picture pixel of setting accounted for temperature area
Several ratios.Different weights is selected for different region characteristics, has reached better display output effect and quick and precisely
The purpose of positioning failure component.
Further, selection uses different visible images under different illuminance, when detecting visible images
Gray value be higher than threshold value when determine current light degree condition it is preferable, it is seen that light image quality is higher, can directly select acquisition
Visible images are handled as visible images to be fused；When detecting the gray value of visible images lower than threshold value
Determine that current light degree condition is poor, it is seen that light image quality is bad, selects the valve module model image data saved at this time
It is handled as visible images to be fused.The method increase imaging display effects.
Detailed description of the invention
Fig. 1 is converter valve components floor plan；
Fig. 2 is converter valve image processing flow figure；
Fig. 3 is building area-of-interest flow chart.
Specific embodiment
To keep the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, to the present invention
It is described in further detail, but real-time mode of the invention is not limited thereto.
Infrared image is radiation image, there are in visible images not it is observed that target, can preferably reflect with
The biggish target of the background temperature difference, but for the unobvious of detail section performance；Visible images are reflected image, background environment
Texture-rich can preferably reflect the details of scene, but contrast is relatively low when illumination is bad.Infrared image and visible
The fusion of light image can there are background informations abundant in characteristic and visible images to have combined by target in infrared image
, their own characteristic information is effectively integrated and is excavated, the understanding to scene is enhanced, protrudes target well.Therefore this hair
Bright focuses on for the visible images of the converter valve components of acquisition and infrared image being fused together, to reach preferably aobvious
Show output effect and the quick and precisely purpose of positioning failure component.
Change of current valve monitoring system of the invention includes visible light lens and infrared lens, rationally designs the phase of both camera lenses
To position and imaging size, it is ensured that the areas imaging of the two is consistent, carries out basis for the processing of subsequent image co-registration.The system
It further include processor, processor is used for after receiving the information that can acquire light microscopic head and infrared lens, does corresponding image
Fusion treatment, converter valve monitoring method as of the invention.
Before doing fusion treatment, the electrical component layout drawing of known converter valve components is stored in advance, by change of current valve group
The plane of part is divided into reactor region and thyristor region, as shown in Figure 1.Wherein, the component size in reactor region
Larger, feature is more obvious in fusion display, is easier to identify；Component size in thyristor region is smaller and more close
Collection is not easily distinguishable in fusion display.For the characteristic in both regions, different method for amalgamation processing will be used below.
Specific method is as shown in Figure 2.
Firstly, the visible light input picture of acquisition is enhanced module, to carry out image enhancement processing.The purpose of image enhancement
It is the visual effect for improving image, the whole or local feature of image is purposefully protruded, so that interested feature is more clear
It embodies clearly, meets the requirement of system.Specifically include stabilization processing and image color processing.
Then, the visible images of image enhancement and infrared image are subjected to coaxial Edge Feature Matching correction process,
Ensure that object exterior contour is consistent when the two imaging superposition, no offset.
Then, the infrared image of acquisition and visible images are divided at least two regions, shape, the number in region can roots
It is split according to actual conditions.For each region, temperature area was filtered out according to infrared image, specific method as shown in figure 3,
That is:
1) for each region Qj, the temperature data of each pixel is calculated by infrared picture data, finds area
Domain QjInterior maximum temperature point Tjmax；
2) temperature data when operating normally converter valve components saves as template, by the maximum temperature point in each region
TjmaxIt makes comparisons with the temperature threshold of template, if more than the temperature threshold of template, which was temperature area, which is stored
For " area-of-interest (Region of Interest, ROI) "；Otherwise, cancel the definition that the region is ROI；
3) each region is judged.
In addition, it is noted that the method for segmentation, region need basic when infrared image and visible images are split
It is completely the same, to reach accurate syncretizing effect.
Secondly, the infrared image of ROI is carried out image enhancement processing.
Finally, according to the spatial layout feature of converter valve components, it will be corresponding in the infrared image of the visible images of ROI and ROI
The gray value of pixel is weighted summation, the image merged.
Assuming that visible images to be fused are expressed as VIS, infrared image is expressed as IR, and fusion results are expressed as
The realization process of Fusion, pixel Weighted Average Algorithm indicate as follows:
Fusion (i, j)=ω1VIS(i,j)+ω2IR(i,j)
Wherein, (i, j) indicates distributing position of the pixel in two-dimensional image matrix, corresponds to the row and column where pixel,
ω1Indicate the weight of visible images, ω2Indicate the weight of infrared image, and ω1+ω2=1.The determination of weight directly affects
Fusion results.
Wherein, specific weight selection method are as follows:
If converter valve components are reactor area, the volume of reactor is relatively large and structure is single, is hardly damaged, here
Weight ω1、ω2Use fixed value.Be specifically configured to how many, can according to Practical Project demand, experience or historical data into
Row setting, to reach preferable syncretizing effect.
If converter valve components are thyristor area, thyristor and its peripheral circuit small volume, area is not easy in infrared image
Point, different weights is used according to the difference of grey scale pixel value.Specific Weight selected method are as follows:
1) due to the gray value of pixel and incident illumination intensity direct proportionality, normal identification is counted before fusion
The grey scale pixel value of the visible images of illuminance 1LUX needed for converter valve components clarity, and as standard value.
2) based on practical converter valve imaging effect, a table is established, which is pixel ratio and visible light figure
The relationship of the weight of picture.Wherein, the visible images grey scale pixel value and standard value of ROI region to be fused are made comparisons, is counted
The ratio that the total pixel of visible images is accounted for lower than the pixel of standard value is calculated, which is pixel ratio.The table can be through more
Secondary actual measurement, empirical statistics go out the best correspondence of the ratio and visual image fusion weight size.The pixel ratio of the table
Example has certain range, not it is all include including.
3) pixel ratio for calculating the visible images of ROI region to be fused obtains visible images according to table
Weight, and then obtain the weight of infrared image.It is possible that calculated pixel ratio does not embody in the table, there are deviations.Example
Such as: what is stored in table is respectively 0.3,0.4,0.5,0.6 pixel ratio and the relationship of visible images weight, and is calculated
The pixel ratio come is 0.37, pixel ratio can be selected for the power of visible images corresponding to 0.4 by nearby principle at this time
Recast is the weight of the secondary visible images.
4) in addition, when calculated pixel ratio is less than minimum threshold, determining to work as when beyond the range of table storage
Preceding illumination condition is slightly poor, it is seen that light image quality is bad, it is seen that light image is unavailable, use the component model that has saved as to
The visible images of fusion.
This method selects different weights according to the characteristic of converter valve components, can be rapidly performed by image co-registration, reaches
Output effect and the quick and precisely purpose of positioning failure component are shown to better, to clearly show that each components
State remains scene detailed information abundant, rapid examination abnormal area component surface feature.
In the specific implementation, can come by adjusting the transparency display scale of infrared image and visible images to image into
Row superposition, it will be seen that light image is as background image, and using infrared image as upper layer images, the image adjusted in ROI region is folded
Proportionality coefficient is added to achieve the purpose that prominent abnormal excess temperature element.
The determination principle of transparency proportion weighted coefficient when two kinds of image co-registrations is, (without exception under accidental conditions
Excess temperature failure), it is seen that light image transparency display scale is lower, and thermal-induced imagery transparency display scale is higher, mainly passes through
Visible images watch real-time running state；There are under abnormal excess temperature fault condition, ROI region visible images transparency is shown
Show that ratio increases, thermal-induced imagery transparency display scale reduces, and shows ROI region element excess temperature failure suddenly.It can also pass through
Human-computer interaction interface manually adjusts the transparency display scale of two kinds of images, to reach better final display effect, and is melting
Close the maximum temperature value that ROI region is marked in image.
It is discussed in detail although the contents of the present invention have passed through above preferred embodiment, but it should be appreciated that above-mentioned
Description is not considered as limitation of the present invention.After those skilled in the art have read above content, for of the invention
A variety of modifications and substitutions all will be apparent.Therefore, protection scope of the present invention should be limited to the appended claims.
Claims (10)
1. a kind of converter valve monitoring method, which comprises the steps of:
1) infrared image and visible images of converter valve components are acquired；
2) converter valve components are divided at least two regions, and temperature area was filtered out according to the infrared image in each region；
3) gray value of corresponding pixel points in the infrared image of the visible images of temperature area and temperature area excessively excessively is weighted
Summation, the image merged；Wherein, it crosses the corresponding weight of visible images of temperature area and crosses the infrared image pair of temperature area
The weight answered adds up to 1.
2. converter valve monitoring method according to claim 1, which is characterized in that when converter valve components are reactor area,
The weight for crossing the visible images of temperature area is fixed value.
3. converter valve monitoring method according to claim 1, which is characterized in that when converter valve components are thyristor area,
The weight for crossing the visible images of temperature area is directly proportional to pixel ratio；Wherein, the pixel ratio was the visible of temperature area
The gray value of light image pixel accounted for the visible images of temperature area lower than the number of the gray value of the standard picture pixel of setting
The ratio of total number of pixels；The gray value of standard picture pixel refers to illumination needed for normally identifying converter valve components clarity
Spend the grey scale pixel value of the visible images of 1LUX.
4. converter valve monitoring method according to claim 1, which is characterized in that step 2) includes: by the red of each region
Outer image is converted to temperature value, searches the maximum temperature in the region, if maximum temperature is greater than temperature threshold when operating normally,
Then the region was temperature area.
5. converter valve monitoring method according to claim 1, which is characterized in that before step 3) further include: by temperature area
Infrared image carry out image enhancement processing.
6. converter valve monitoring method according to claim 1, which is characterized in that before step 2) further include: by acquisition can
Light-exposed image carries out image enhancement processing.
7. converter valve monitoring method according to claim 5 or 6, which is characterized in that described image enhancing processing includes anti-
Tremble processing and image color processing.
8. converter valve monitoring method according to claim 3, which is characterized in that when the pixel ratio is lower than setting ratio
When, the visible images of acquisition are abandoned, using the history visible images of storage as visible images to be fused.
9. converter valve monitoring method according to claim 1, which is characterized in that before step 2) further include: by acquisition can
Light-exposed image and infrared image carry out coaxial edge feature geometric precision correction processing.
10. a kind of change of current valve monitoring system, which is characterized in that including acquisition unit and processor, the acquisition unit includes can
Light-exposed camera lens and infrared lens；The processor sampling connects the visible light lens and infrared lens；
The visible light lens are used to acquire the visible images of converter valve components, and the infrared lens are for acquiring change of current valve group
The infrared image of part；
The processor is used to converter valve components being divided at least two regions, and is filtered out according to the infrared image in each region
Cross temperature area；The gray value of corresponding pixel points in the infrared image of the visible images of temperature area and temperature area excessively excessively is added
Power summation, the image merged；Wherein, it crosses the corresponding weight of visible images of temperature area and crosses the infrared image of temperature area
Corresponding weight adds up to 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710612787.0A CN107478340B (en) | 2017-07-25 | 2017-07-25 | A kind of converter valve monitoring method and system based on image co-registration |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710612787.0A CN107478340B (en) | 2017-07-25 | 2017-07-25 | A kind of converter valve monitoring method and system based on image co-registration |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107478340A CN107478340A (en) | 2017-12-15 |
| CN107478340B true CN107478340B (en) | 2019-08-06 |
Family
ID=60596677
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710612787.0A Active CN107478340B (en) | 2017-07-25 | 2017-07-25 | A kind of converter valve monitoring method and system based on image co-registration |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107478340B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108332858B (en) * | 2018-01-10 | 2020-04-10 | 云南电网有限责任公司电力科学研究院 | Valve cooling system monitoring method and system |
| CN108983110B (en) * | 2018-04-16 | 2020-10-27 | 许继集团有限公司 | Power supply reliability detection system of converter valve monitoring equipment |
| CN108428222A (en) * | 2018-05-21 | 2018-08-21 | 深圳市神飞电子科技有限公司 | A kind of system of Terahertz image and natural light image superposition |
| CN109146904A (en) * | 2018-08-13 | 2019-01-04 | 合肥英睿系统技术有限公司 | The method and apparatus of infrared image object profile is shown in visible images |
| WO2020061789A1 (en) * | 2018-09-26 | 2020-04-02 | 深圳市大疆创新科技有限公司 | Image processing method and device, unmanned aerial vehicle, system and storage medium |
| CN111433810A (en) | 2018-12-04 | 2020-07-17 | 深圳市大疆创新科技有限公司 | Target image acquisition method, shooting device and unmanned aerial vehicle |
| CN109636797B (en) * | 2018-12-21 | 2022-08-05 | 国网福建省电力有限公司 | Method for detecting deformation of non-contact flexible direct current converter valve module |
| CN112798880A (en) * | 2019-11-14 | 2021-05-14 | 许继集团有限公司 | Monitoring method and system for key elements in converter valve |
| CN111179267B (en) * | 2020-01-22 | 2023-05-12 | 湘潭大学 | Quality monitoring method for part surface laser cladding manufacturing process |
| CN111436972A (en) * | 2020-04-13 | 2020-07-24 | 王时灿 | Three-dimensional ultrasonic gynecological disease diagnosis device |
| CN111798560B (en) * | 2020-06-09 | 2023-09-01 | 同济大学 | Visualization method for three-dimensional live-action model of infrared thermal image temperature measurement data of power equipment |
| CN112304364A (en) * | 2020-09-24 | 2021-02-02 | 许继集团有限公司 | Panoramic inspection method for energy-consuming converter valve and monitoring device for energy-consuming converter valve |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2271073B1 (en) * | 2009-07-01 | 2018-03-07 | Fluke Corporation | Thermography methods |
| CN103778618A (en) * | 2013-11-04 | 2014-05-07 | 国家电网公司 | Method for fusing visible image and infrared image |
| CN104217425B (en) * | 2014-08-15 | 2017-02-01 | 国家电网公司 | Superpixel-based electric transmission and transformation equipment infrared fault image segmentation method |
| CN204178238U (en) * | 2014-10-21 | 2015-02-25 | 山东鲁能智能技术有限公司 | A kind of suspension cable type intelligent inspection robot for converter station valve hall equipment |
| CN105160792B (en) * | 2015-07-30 | 2019-03-29 | 国家电网公司 | A kind of monitoring system of electricity grid substation |
| CN106960428A (en) * | 2016-01-12 | 2017-07-18 | 浙江大立科技股份有限公司 | Visible ray and infrared double-waveband image co-registration Enhancement Method |
| CN106548467B (en) * | 2016-10-31 | 2019-05-14 | 广州飒特红外股份有限公司 | The method and device of infrared image and visual image fusion |
| CN206148959U (en) * | 2016-11-21 | 2017-05-03 | 南方电网科学研究院有限责任公司 | Current conversion station |
-
2017
- 2017-07-25 CN CN201710612787.0A patent/CN107478340B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN107478340A (en) | 2017-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107478340B (en) | A kind of converter valve monitoring method and system based on image co-registration | |
| CN112734692B (en) | Defect identification method and device for power transformation equipment | |
| CN106548467B (en) | The method and device of infrared image and visual image fusion | |
| CN111275759B (en) | Transformer substation disconnecting link temperature detection method based on unmanned aerial vehicle double-light image fusion | |
| CN110850723B (en) | Fault diagnosis and positioning method based on transformer substation inspection robot system | |
| CN104168478B (en) | Based on the video image color cast detection method of Lab space and relevance function | |
| CN109800697B (en) | Transformer target detection and appearance defect identification method based on VGG-net style migration | |
| CN111260788B (en) | Power distribution cabinet switch state identification method based on binocular vision | |
| CN107907775B (en) | Wiring detection method and wiring detection device | |
| CN106056594A (en) | Double-spectrum-based visible light image extraction system and method | |
| CN115290696A (en) | Infrared thermal imaging defect detection method and device for transformer substation insulator | |
| CN104834081B (en) | Rapid automatic focusing method for stereoscopic microscope | |
| Kurmi et al. | Pose error reduction for focus enhancement in thermal synthetic aperture visualization | |
| CN116310274A (en) | State evaluation method for power transmission and transformation equipment | |
| CN113778091A (en) | Method for inspecting equipment of wind power plant booster station | |
| Zhou et al. | Calibration and location analysis of a heterogeneous binocular stereo vision system | |
| CN110956640B (en) | Heterogeneous image edge point detection and registration method | |
| CN104457653A (en) | Displacement detection method for valve element of linear electromagnetic valve | |
| CN108154478A (en) | A kind of remote sensing image processing method | |
| CN107833204B (en) | Visual detection method of infrared image of substation equipment based on topology matching | |
| CN102679957B (en) | Background information and color feature combined fish body detection method | |
| Gao et al. | Method of quality assessment based on convolution feature similarity for laser disturbing image | |
| CN103778594A (en) | Red-eye detection method based on flashlight and non-flashlight image pairs | |
| CN114418941B (en) | Defect diagnosis method and system based on detection data of power inspection equipment | |
| CN117706239B (en) | Converter transformer overheat fault point prediction system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |